fix nan in optimizer_on_cpu

examples/run_squad.py

@@ -687,6 +687,7 @@ def set_optimizer_params_grad(named_params_optimizer, named_params_model, test_n
         if name_opti != name_model:
             logger.error("name_opti != name_model: {} {}".format(name_opti, name_model))
             raise ValueError
+        if param_model.grad is not None:
             if test_nan and torch.isnan(param_model.grad).sum() > 0:
                 is_nan = True
             if param_opti.grad is None: